Commits · 5caaeb714ce3fd08de9c2e87848b4825bb4b676d · OpenDAS / vllm_cscc

"docs/vscode:/vscode.git/clone" did not exist on "7e06c40e63c12c0ea5fb400fa8f06007e90ff84f"

24 Sep, 2025 14 commits
- [Bugfix] [Frontend] Cleanup gpt-oss non-streaming chat tool calls (#25514) · 5caaeb71
  Ben Browning authored Sep 23, 2025
```
Signed-off-by: Ben Browning <bbrownin@redhat.com>
```
  5caaeb71
- [Perf] Fix jit compiles at runtime of fla gated delta rule (#25432) · d747c2ef
  Corey Lowman authored Sep 23, 2025
```
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  d747c2ef
- [Spec Decode] Enable FlashInfer Spec Decoding (#25196) · c30b405b
  Benjamin Chislett authored Sep 23, 2025
```
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Co-authored-by: lhsjohn <huashuoli@tencent.com>
```
  c30b405b
- [KV sharing] Re-land Gemma3n model changes from #22628 (#24357) · 77d90699
  Yong Hoon Shin authored Sep 23, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  77d90699
- [fix]: add Arm 4bit fused moe support (#23809) · 359d2930
  Nikhil Gupta authored Sep 24, 2025
```
Signed-off-by: Nikhil Gupta <nikhil.gupta2@arm.com>
```
  359d2930
- [BugFix] Fix MLA assert with CUTLASS MLA (#25478) · 9df8da54
  Lucas Wilkinson authored Sep 23, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  9df8da54
- [Core] Support weight_loader_v2 for `UnquantizedLinearMethod` (#23036) · de94289a
  Kyle Sayers authored Sep 24, 2025
```
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
```
  de94289a
- [Bugfix] Use a separate FlashInfer workspace buffer for trtllm-gen (#25520) · 19836092
  Benjamin Chislett authored Sep 23, 2025
  
  19836092
- [V1][Metrics] Add per-request TPOT histogram (#24015) · d06b5a95
  baxingpiaochong authored Sep 24, 2025
```
Signed-off-by: baxingpiaochong <771405853@qq.com>
```
  d06b5a95
- [Model] Support SeedOss Reason Parser (#24263) · be0bb568
  0xNullPath authored Sep 24, 2025
```
Signed-off-by: Yan Lu <luyan@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  be0bb568
- [BUG] Allows for RunAI Streamer and Torch.compile cache to be used together (#24922) · c8bde933
  ahao-anyscale authored Sep 23, 2025
```
Signed-off-by: ahao-anyscale <ahao@anyscale.com>
```
  c8bde933
- [Bug] Fix AttributeError: 'FusedMoE' object has no attribute... · 88d7bdbd
  Wentao Ye authored Sep 23, 2025
```
[Bug] Fix AttributeError: 'FusedMoE' object has no attribute 'w13_weight_scale'. Did you mean: 'w13_weight_scale_inv' (#25519)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  88d7bdbd
- Add CUTLASS FP8 MOE benchmark scripts and kernel config (#25302) · 0d235b87
  Chenxi Yang authored Sep 23, 2025
```
Signed-off-by: Chenxi Yang <cxyang@fb.com>
Co-authored-by: Chenxi Yang <cxyang@fb.com>
```
  0d235b87
- [BugFix] AssertionError: Do not capture num_reqs > max_num_reqs for uniform batch (#25505) · dc464a3d
  Lucas Wilkinson authored Sep 23, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  dc464a3d
23 Sep, 2025 26 commits
- [Perf] Increase default max splits for FA3 full cudagraphs (#25495) · e0b24ea0
  Lucas Wilkinson authored Sep 23, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  e0b24ea0
- [ROCm] Small functional changes for gptoss (#25201) · bde2a1a8
  Juan Villamizar authored Sep 23, 2025
```
Signed-off-by: jpvillam <jpvillam@amd.com>
Co-authored-by: jpvillam <jpvillam@amd.com>
```
  bde2a1a8
- [Kernel] [Mamba] Remove BLOCK_H=1 from list of tuneable configurations for... · 5e25b122
  Thomas Parnell authored Sep 24, 2025
```
[Kernel] [Mamba] Remove BLOCK_H=1 from list of tuneable configurations for `_chunk_cumsum_fwd_kernel` (#25197)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Chih-Chieh-Yang <chih.chieh.yang@ibm.com>
```
  5e25b122
- Add `VLLM_NVTX_SCOPES_FOR_PROFILING=1` to enable `nvtx.annotate` scopes (#25501) · c85d75cf
  Corey Lowman authored Sep 23, 2025
```
Signed-off-by: Corey Lowman <clowman1993@gmail.com>
```
  c85d75cf
- [BugFix] Fix OOM in vLLM replicas by ensuring consistent NCCL memory accounting (#25359) · abad204b
  kourosh hakhamaneshi authored Sep 23, 2025
```
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
```
  abad204b
- Remove redundant mutates_args and dispatch_key for direct_register_custom_op (#25512) · 7361ab37
  Michael Goin authored Sep 23, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  7361ab37
- [gpt-oss][bugfix] remove logic to require resp_ in ResponseAPI (#25428) · 95bc60e4
  Andrew Xia authored Sep 23, 2025
```
Signed-off-by: Andrew Xia <axia@meta.com>
```
  95bc60e4
- Fix triton_reshape_and_cache_flash.py triton import (#25522) · 4f2954f7
  Michael Goin authored Sep 23, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  4f2954f7
- Add VLLM_ENABLE_INDUCTOR_MAX_AUTOTUNE & VLLM_ENABLE_INDUCTOR_COORDINA… (#25493) · eca7be90
  rouchenzi authored Sep 23, 2025
```
Signed-off-by: rouchenzi <ruochenwen@gmail.com>
Signed-off-by: rouchenzi <40842833+rouchenzi@users.noreply.github.com>
```
  eca7be90
- [V0 Deprecation] Remove placeholder attn (#25510) · 969b4da3
  Thomas Parnell authored Sep 24, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  969b4da3
- [Core] Use KVCacheBlock as much as possible instead of dict[block_id, KVCacheBlock] (#24830) · 4f8c4b89
  Jialin Ouyang authored Sep 23, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
  4f8c4b89
- [CI/Build] Fix and re-enable v1 PP test on CI (#25496) · ae002924
  Isotr0py authored Sep 24, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  ae002924
- [Bugfix] Fix for the import error from #24588 (#25481) · 690f948e
  Gregory Shtrasberg authored Sep 23, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  690f948e
- [Build] Update Xgrammar to 0.1.25 (#25467) · 08275ec0
  Chauncey authored Sep 24, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  08275ec0
- [Bugfix] gpt-oss container tool output bug (#25485) · c828d1bf
  Alec S authored Sep 23, 2025
```
Signed-off-by: Alec Solder <alecs@fb.com>
Co-authored-by: Alec Solder <alecs@fb.com>
```
  c828d1bf
- [CI] Fix Pre-commit Issue (#25497) · 8b8a8afc
  Wentao Ye authored Sep 23, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  8b8a8afc
- Enable symmetric memory all reduce by default only enabling for TP (#25070) · 8bdd8b5c
  Ilya Markov authored Sep 23, 2025
```
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  8bdd8b5c
- [Bugfix] Lower gpt-oss max cudagraph size to 992 to be compatible with FA3 (#25508) · a8ffc4f0
  Michael Goin authored Sep 23, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  a8ffc4f0
- [Speculators][Speculative Decoding] Fix gpt-oss eagle3 accuracy issue (#25406) · d5944d51
  jiahanc authored Sep 23, 2025
```
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
```
  d5944d51
- [Perf] Change default CUDAGraphMode from PIECEWISE to FULL_AND_PIECEWISE (#25444) · 24fab45d
  Michael Goin authored Sep 23, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  24fab45d
- [Performance] Move apply_w8a8_block_fp8_linear to an op class (#24666) · 63400259
  ElizaWszola authored Sep 23, 2025
```
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: ElizaWszola <elizaw.9289@gmail.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
```
  63400259
- [core] add nccl symmetric memory for all reduce (#24532) · 8c1c81a3
  Amir Samani authored Sep 23, 2025
```
Signed-off-by: Amir Samani <asamani@nvidia.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  8c1c81a3
- [ROCm] Add skinny gemm bias support for dtypes fp16,bf16,fp8 (#24988) · a3a78280
  Hashem Hashemi authored Sep 23, 2025
```
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
Signed-off-by: Hashem Hashemi <159079214+amd-hhashemi@users.noreply.github.com>
```
  a3a78280
- [Core] Ensure LoRA linear respect the base_layer's tp_size and tp_rank (#25487) · 5abb1179
  Jee Jee Li authored Sep 24, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  5abb1179
- [V1][Kernel] Add triton implementation for `reshape_and_cache_flash` (#24503) · 100b630a
  Burkhard Ringlein authored Sep 23, 2025
```
Signed-off-by: Burkhard Ringlein <ngl@zurich.ibm.com>
Co-authored-by: Chih-Chieh Yang <chih.chieh.yang@ibm.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
  100b630a
- [Log] Optimize kv cache memory log from Bytes to GiB (#25204) · 846197f5
  Wentao Ye authored Sep 23, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  846197f5